IAPR TC11 Newsletter 2018 5
- Message from the Editor
- Dates and Deadlines
- Upcoming Conferences
- Call for Participation: 2nd Summer School on Document Analysis
- Calls for Proposals
- Call for Proposals to Host DAS 2020
- Call for Proposals to Host ICFHR 2022
- ICPR 2018 Robust Reading for Multi-Type Web Images (MTWI) Challenge: Call for Participation
- Call for Papers: Seventh IAPR International Workshop on Computational Forensics (@ICPR)
- Call for Submissions: Int'l Workshop on Music Reading Systems (WoRMS)
- IJDAR: New Issue (Vol. 21, Issue 1)
- IJDAR Discount for IAPR Members (repost)
- Univ. Rouen (France): Research Engineer / PostDoc Position
- Student Industrial Internship Opportunities (IAPR) - (repost)
Greetings! Happily, there are many interesting events to share in this edition of the TC-11 newsletter.
DAS 2018 in Vienna was a great success! Please have a look at the conference web pages (https://das2018.cvl.tuwien.ac.at/en) and Twitter page (https://twitter.com/DASWorkshop) for details. Congratulations to the DAS award winners:
- The Best Student Paper Award went to Daniel Stromer for the paper entitled “Non-Destructive Digitization of Soiled Historical Chinese Bamboo Scrolls” https://twitter.com/DASWorkshop/status/989887099875876864
- The Nakano Best Paper Award went to Praveen Krishnan, Katrik Dutta, and C. V. Jawahar for the paper entitled “Word spotting and recognition using deep embedding” https://twitter.com/DASWorkshop/status/989578856322433025
Our next TC-11 meeting is being held this August in Niagara Falls at the International Conference on Frontiers in Handwriting Recognition (ICFHR). The conference program and registration have now been posted, and a Twitter page has been set up (https://twitter.com/icfhr2018). Early registration ends June 15th. We have two very exciting keynote speakers, Kevin Knight (a leader in NLP research) and Gregory R. Crane (a leader in the Digital Humanities). Please consider attending what promises to be an excellent meeting.
Calls for Proposals to Host DAS & ICFHR. Bids to host the next DAS and ICFHR can be found elsewhere in this newsletter. The deadlines are relatively soon (July 1 for ICFHR, July 15 for DAS).
Summer School. Registration for the Document Analysis and Recognition Summer School being held in La Rochelle, France ends on June 15th. If you are interested, please visit the web pages soon: http://ssda.univ-lr.fr. This will be our 2nd summer school, after the very successful summer school held in India last summer.
WoRMS. A new workshop related to the recognition of musical notation and musicians using the technology will be held this September. Please visit the workshop web page for details: https://sites.google.com/view/worms2018. This is a nice development, after the strong representation by Optical Music Recognition (OMR) researchers at GREC 2017.
IJDAR. The latest issue of IJDAR has just been released. The Table of Contents and links to papers are provided in the newsletter.
Enjoy all of the new posts, and I’ll talk to you again soon.
Richard Zanibbi, TC-11 Communications Officer
( email@example.com )
- June 15, 2018: Registration deadline for Summer School on Document Analysis (SSDA)
- July 1, 2018: Call for bids to host ICFHR 2022
- July 15, 2018: Call for bids to host DAS 2022
- July 15, 2018: Abstracts due for WoRMS (Call for Submissions)
- ICFHR 2018. Niagara Falls, USA (August 5-8, 2018)
- ICPR 2018. Beijing, China (August 20-24, 2018)
- DocEng 2018. Halifax, Canada (August 28-31, 2018)
- WoRMS 2018. Paris, France (Sept. 20, 2018)
2019 and Later
- ICDAR 2019, Sydney, Australia (September 22-25, 2019)
- ICFHR 2020. Dortmund, Germany (September 8-10, 2020)
2nd Summer School on Document Analysis: Traditional Approaches and New Trends Location: La Rochelle, France Organised by: L3i Laboratory
(Endorsed by TC10 and TC11)
Web Page: http://ssda.univ-lr.fr
30 May, 2018 Early registration 15 June, 2018 Registration close 2-6 July, 2018 Summer School
We are pleased to announce that the 2nd TC10/TC11 Summer School on Document Analysis and Recognition, endorsed by IAPR TC-10 (Technical Committee on Graphics Recognition) and IAPR TC-11 (Reading Systems) will be held at the University of La Rochelle (France) from July 2nd to 6th, 2018. SSDA 2018 will continue the tradition of the past summer school held in Jaipur (India) in 2017.
This summer school will offer new students in the field of DAR (Document Analysis and Recognition) an overview of all the traditional approaches to process and analyse documents on the one hand, and a necessary overview of new trends in the field (such as deep learning, human document interaction, and forensics).
To reach this objective, lecturers will present classical approaches from the field and classes dedicated to new trends and their point of view for the future of DAR. All the lectures and all the events will be in English.
The school will address the following topics.
- Content representation and manipulation
- Document indexing/retrieval in large corpus of documents
- Machine learning for document analysis and understanding
- Review of OCR methods and handwriting recognition techniques
- Historical documents and new challenges
- Human document interactions
- Text and graphics recognition in a complex environment
There will also be talks from industrial experts.
- David Doermann, USA
- Andreas Fischer, Switzerland
- Dimosthenis Karatzas, Spain
- Bart Lamiroy,France
- Jean-Marc Ogier, France
- Vincent Poulain d’Andecy, France
- Jean-Yves Ramel, France
- Marçal Russiñol, Spain
- Seiichi Uchida, Japan
Jean-Christophe Burie, General Chair, SSDA 2018
( firstname.lastname@example.org )
Call for Proposals to Host DAS 2020
July 15, 2018 Proposal submission deadline
Overview. Following the successful organisation of the 13th IAPR International Workshop on Document Analysis Systems in Vienna (Austria) by General Chairs Robert Sablatnig and Florian Kleber, we are now soliciting proposals for organising and hosting DAS 2020.
The DAS workshop is one of the signature events of TC-11. DAS 2020 will build on the tradition established by past DAS workshops held in Kaiserslautern, Germany (1994), Malvern, PA (1996), Nagano, Japan (1998), Rio de Janeiro, Brazil (2000), Princeton, NJ (2002), Florence, Italy (2004), Nelson, New Zealand (2006), Nara, Japan (2008), Boston, MA (2010), and Gold Coast, Australia (2012), Tours-Loire Valley, France (2014), Santorini, Greece (2016), and Vienna, Austria (2018).
Proposals. Individuals and groups interested in Document Analysis Systems are invited to submit proposals for organizing and hosting DAS 2020. The event will preferably take place in late summer/fall, but is not limited to this period. Extra care should be taken that other events of the community taking place during the same year (e.g. ICPR and ICFHR).
The submission deadline is July 15th, 2018. Proposals should be submitted to the TC11 chair (Dimosthenis Karatzas) and vice-chair (Masakazu Iwamura).
If you already know whether you are interested in preparing a proposal, please send us an email expressing your interest. Note that an expression of interest is not a commitment to make a formal proposal nor an official bid. If you need further information concerning DAS, please feel free to contact us.
Selection. The final selection among competing proposals will be made short after the deadline by the DAS Steering Committee, which is composed of all those who have themselves organized or contributed substantially to past DAS workshops.
Call for Proposals to Host ICFHR 2022
July 1, 2018 Proposal submission deadline
Overview. Continuing a long tradition, the international research community plans to gather in Niagara Falls, USA, for the 16th International Conference on Frontiers in Handwriting Recognition on August 5-8, 2016 (http://icfhr2018.org). In keeping with the practice of the community, proposals are now being solicited for hosting ICFHR 2022, the 18th International Conference on Frontiers in Handwriting Recognition.
ICFHR is the premier event for identifying, encouraging, and exchanging ideas in handwriting recognition research, as well as for promoting novel applications at the frontiers of this important field. The single-track conference brings together leading researchers and practitioners in on-line and off-line handwriting recognition.
The series of the ICFHR conferences is a continuation of the ten IWFHRs (Montreal 1990, Chateau de Bonas 1991, Buffalo 1993, Taipei 1994, Colchester 1996, Taejon 1998, Amsterdam 2000, Niagara on the Lake 2002, Tokyo 2004, La Baule 2006). Previous ICFHR conferences were held in Montreal 2008, Kolkata 2010, Bari 2012, Crete 2014, and Shenzhen 2016. The 17th International Conference on Frontiers in Handwriting Recognition, ICFHR 2020, is scheduled to be held in Dortmund, Germany, on September 8-10, 2020.
Proposals. Individuals and groups who are interested in handwriting recognition research are invited to submit proposals for organizing and hosting ICFHR 2022. According to the normal rotation, the year 2022 would see the conference located somewhere in Asia, but proposals from other locales are encouraged as well.
Teams interested in making a proposal should express their interest to do so as soon as possible. Finalized proposals should be sent to: Dimosthenis Karatzas, TC-11 Chair, email@example.com, and Masakazu Iwamura, TC-11 Vice Chair, firstname.lastname@example.org.
In addition, proposers should be prepared to make a brief presentation to the community during a special session at ICFHR 2018 after which a vote will be taken to determine the winning bid (ICFHR 2018 Program) on the last day of the conference.
ICPR 2018 Robust Reading for Multi-Type Web Images (MTWI) Challenge: Call for Participation
Feb. 10, 2018: Registration open Mar 15, 2018: Training data available May 14, 2018: Testing data available and submission open 10:00 UTC+8 on May 17, May 21 and May 23, 2018: three times evaluation and leaderboard update May 23, 2018: Registration close, report submission opens for Top 10 teams May 26, 2018: Report submission deadline June 1, 2018: Results announcement August 20-24, 2018: Workshop and awards ceremony at ICPR 2018
The rapid development of the Internet has facilitated many niches and conveniences, such as online stores, advertisements and so on. The essential information is usually conveyed by the text inside the web images, which makes the text detection and recognition a very important issue. The competition will select typical web images and construct a large-scale web images based dataset for assessing and incenting methods to detect and recognize multi-type web text. There are three tasks of the ICPR 2018 MTWI Challenge under the topic of robust reading for multi-type web images:
- Task 1: Web Images Text Line Recognition
- Task 2: Web Images Text Detection
- Task 3: End-to-End Web Images Text Detection and Recognition
The registration, submission, evaluation and awarding processes of the three tasks are completely independent.
Additional Information and Registration can be found on the competition web page: https://tianchi.aliyun.com/markets/tianchi/icpr_mtwi_2018_challenge
Call for Papers: Seventh IAPR International Workshop on Computational Forensics (@ICPR)
IAPR Workshop on Computational Forensics
August 20, 2018 - Beijing, China
Organized by IAPR Technical Committee (TC-6) on Computational Forensics
July 22, 2018 Paper Submission deadline July 9, 2018 Notification of acceptance July 20, 2018 Camera-ready submission
Overview. With the advent of high-end technology, fraudulent efforts are on rise in many areas of our daily life, may it be fake paper documents, forgery in the digital domain or copyright infringement. In solving the related criminal cases use of pattern recognition (PR) principles is also gaining an important place because of their ability in successfully assisting the forensic experts to solve many of such cases.
The 7th IAPR International Workshop on Computational Forensics (IWCF) will aim at addressing the theoretical and practical issues related to this field, i.e. role of PR techniques for analyzing problems in forensics. Effort is to bring the people together who are working on these issues in different areas including document and speech processing, music analysis, digital security, forensic sciences, etc.
Areas of Interest. Some broad areas of interest include (but are not limited to):
- Detection of fake documents
- Authentication of security documents
- Change detection
- Copyright protection
- Encryption and watermarking
- Digital forensics
- Encryption and watermarking
- Handwriting and Speech analysis
- Face, Palm, and Iris recognition
- Anti-forensics and anti-anti-forensics Techniques
- Data leakage, Data protection and Database forensics
- Investigation of Virtual and Cloud Environments
- Malware forensics
- SDN forensics
- Mobile device forensics
- Change detection
- Cyber threat intelligence
- Large-Scale cyber investigations
- Network forensics and network traffic analysis
Like in previous years, the workshop will be a place for elaborate discussion of academic and industrial works, documenting the advances in the related field and creating mutual collaboration on related areas. Interaction among practitioners and academic researchers will receive special attention in this workshop.
Paper Submission. Springer will proceed with the publication of the ICPR workshops proceedings in the LNCS series after the workshop. There will be an informal proceeding during the workshop for communications and finally the proceeding will be published.
Full papers should describe complete works of original research. Authors are invited to submit original, unpublished research papers that are not being considered in another forum.The submission format should follow the LNCS Springer layout (see instructions here) with length from 12 to 14 pages .
Authors may submit short papers providing an opportunity to report on research in progress, to present novel positions or a demonstration proposal. The submission format should follow the LNCS Springer layout (see instructions here) with length from 6 to 8 pages.
Jean-Marc Ogier, University of La Rochelle, France
Chang-Tsun Li, Charles Sturt University
Nicolas Sidère, University of La Rochelle, France
Jean-Marc Ogier, Organizing Committee Member
( email@example.com )
15 July, 2018 Abstract submission deadline 15 July, 2018 Registration deadline 20 Sept, 2018 Workshop
It is our pleasure to announce the 1st International Workshop on Music Reading Systems (WoRMS). It will take place on Thursday, the 20th of September 2018, at the Conservatoire national des arts et métiers (292 Rue Saint-Martin, 75003 Paris), as a satellite event to ISMIR 2018.
WoRMS is a new workshop that tries to connect researchers who develop music reading systems — especially from the field of optical music recognition, but also related topics such as score following or cross-modal retrieval — with researchers and practitioners that could benefit from such systems, like librarians or musicologists.
WoRMS will be organized as a one-day workshop and we hope it will provide a novel opportunity to share ideas, discuss current developments and shape the future of music reading systems. We would like for diverse points of view to engage, by explicitly inviting contributors without a technical background to participate as well.
We strive to make the workshop as interactive as possible, with participants getting the opportunity not just to present their work, but to discuss current research in depth and foster relationships within the community. Therefore, promising ideas, work-in-progress submissions and recently submitted or published works are equally welcome. In order to promote discussion, we will use OpenReview (the full Call for Submissions is available at https://sites.google.com/view/worms2018/call-for-papers).
Please check the website https://sites.google.com/view/worms2018 for further information. In order to help us organizing the workshop, we kindly ask you to register before the 15th of July, if you plan on attending WoRMS, here: https://sites.google.com/view/worms2018/attending.
Please feel free to forward this announcement to anyone who might be interested.
IJDAR: New Issue (Vol. 21, Issue 1)
Table of Contents
Click on the links to go directly to the Springer Link page for each article.
Text and non-text separation in offline document images: a survey. Showmik Bhowmik, Ram Sarkar, Mita Nasipuri & David Doermann
Recognition-based character segmentation for multi-level writing style. Papangkorn Inkeaw, Jakramate Bootkrajang, Phasit Charoenkwan, Sanparith Marukatat, Shinn-Ying Ho & Jeerayut Chaijaruwanich
Efficient document image binarization using heterogeneous computing and parameter tuning. Florian Westphal, Håkan Grahn & Niklas Lavesson
Making scanned Arabic documents machine accessible using an ensemble of SVM classifiers. Randa Elanwar, Wenda Qin & Margrit Betke
A novel Arabic OCR post-processing using rule-based and word context techniques. Iyad Abu Doush, Faisal Alkhateeb & Anwaar Hamdi Gharaibeh
Text box proposals for handwritten word spotting from documents. Suman Ghosh & Ernest Valveny
Fusion of LLE and stochastic LEM for Persian handwritten digits recognition. Rassoul Hajizadeh, A. Aghagolzadeh & M. Ezoji
Binarization of degraded document images based on contrast enhancement. Di Lu, Xin Huang & LiXue Sui
Handling noise in textual image resolution enhancement using online and offline learned dictionaries. Rim Walha, Fadoua Drira, Frank Lebourgeois, Christophe Garcia & Adel M. Alimi
IJDAR Discount for IAPR Members (repost)
IAPR is pleased to announce a partnership agreement with Springer, the publisher of IJDAR, the International Journal on Document Analysis and Recognition. This new agreement will allow IAPR members to receive a subscription to the electronic version of IJDAR at a discount of nearly 50%. For additional details, see the links below:
TC-11 maintains a colletion of datasets that can be found online in the TC-11 Datasets Repository.
If you have new datasets (e.g., from competitions) that you wish to share with the research community, please contact the TC-11 Dataset Curator (contact information is below).
Andreas Fischer (TC-11 Dataset Curator)
Univ. Rouen (France): Research Engineer / PostDoc Position
Information extraction, Text Recognition in Historical Document Collections
April 1, 2018 - October 19, 2019 Contract period, renewable to Mar. 2021
LITIS (Laboratoire d’Informatique, Traitement de l’information et des Systèmes) is a research laboratory associated to the University of Rouen Normandie, Le Havre Normandie Normandie, and School of Engineering INSA Rouen Normandie. Research at LITIS is organized around 7 research teams which contribute to 3 main application domains: Access to Information, Biomedical Information Processing, Ambient Intelligence. LITIS currently includes 90 faculty staff members, 50 PhD students, 10 PostDoc and Research Engineers. The Machine Learning team of LITIS is developing research in modeling unstructured data (signals, images, text, etc…) with machine learning algorithms and statistical models. For more than two decades it has contributed to the development of reading systems and document image analysis for various applications such as postal automation, business document exchange, digital libraries, etc…
The EURHISFIRM project aims at developing a research infrastructure to connect, collect, collate, align, and share reliable long-run company-level data for Europe to enable researchers, policymakers and other stakeholders to analyze, develop, and evaluate effective strategies to promote investment and economic growth. To achieve this goal, EURHISFIRM develops innovative tools to spark a “Big data” revolution in the historical social sciences and to open access to cultural heritage.
EURHISFIRM is funded by the European Commission within the Infrastructure Development Program of Horizon 2020. The goal of the Program is to develop world-class research infrastructures lasting for decades (https://ec.europa.eu/research/infrastructures/index_en.cfm?pg=home ). Research infrastructures are facilities, resources and services used by the science community to foster innovation and extend the frontiers of knowledge.
The first phase of the Infrastructure Development Program lasts for three years. It aims at developing an in-depth design study of the Research Infrastructure. After this phase, Development and Consolidation Phases follow if further applications will be successful. EURHISFIRM brings together eleven research institutions in economics, history, information technologies and data science from seven European countries.
Position to be filled.
Position: Post-Doctoral fellow
Time commitment: Full-time
Duration of the contract: April 1st 2018 – October 2019, (renewable contract until March of 2021)
Contact: Prof. Thierry Paquet, Thierry.Paquet@univ-rouen.fr Indicative salary: €36 000 gross annual salary, with social security benefits
Location: LITIS, Campus du Madrillet, Faculty of science, Saint Etienne du Rouvray, France
Within the project, you will be in charge of developing text information recognition technologies (ICR) from historical document images (mostly printed), and information extraction from these data (such as person names, names of companies, dates, positions, stock prices etc…). The datasets are made of financial yearbooks and price lists of European companies, in different European languages. Your mission includes:
- The development of a machine learning based reading system of text lines composed of both deep optical models, and language models (statistical, and grammar based). Layout analysis falls out of the scope of the mission.
- Data preparation for evaluation purposes
- Benchmarking with other technologies (commercial products)
- Integration of the system as a web service allowing its integration and deployment into a full system
- Coordination with partners of the project regarding datasets preparation and collation of datasets, as well as software interoperability with other developments within the EurHisFirm consortium.
The successful applicant should have a strong record in statistical machine learning and have experience in one popular platform and programming language in the field, so as to design, develop and make the prototype evolve.
- PhD, or Computer Engineer, with a good record in Machine Learning
- Demonstrates ability to work in a team, curious and rigorous spirit
- Excellent written and verbal communication skills (French and English)
( Thierry.Paquet@univ-rouen.fr )
Student Industrial Internship Opportunities (IAPR) - (repost)
IAPR’s Industrial Liaison Committee is pleased to announce the opening of its Company Internship Brokerage List.
The web page lists internship opportunities for students at different levels of education and specialism. We expect many additional internship opportunities to be listed here as the community becomes more aware of the site.
IAPR Company Internship Brokerage List:
Bob Fisher, Chair, IAPR Industrial Liason Committee
( firstname.lastname@example.org )
Call for Contributions: To contribute news items, please send a short email to the editor, Richard Zanibbi (). Contributions might include conference and workshop announcements/updates/reports, career opportunities, book reviews, or anything else of interest to the TC-11 community.
Subscription: This newsletter is sent to subscribers of the IAPR TC11 mailing list. To join the TC-11 mailing list, please click on this link: Join the TC-11 Mailing List. To manage your subscription, please visit the mailing list homepage: TC-11 Mailing List Homepage.